The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for running tests (npm run test and npx playwright test). These are standard operations for development workflows and are strictly scoped to the specific test files being authored.
[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill follows established testing best practices and operates within expected development boundaries.
[INDIRECT_PROMPT_INJECTION]: The skill ingests feature descriptions and existing code to generate test cases. While this represents a data ingestion surface, it is necessary for the skill's primary function and does not contain exploitable capabilities beyond the intended scope.

test-writing